Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -24,7 +24,9 @@ It replaces the older Pyrrho g5 multitask shape with four v2 heads:
|
|
| 24 |
|
| 25 |
The model is intended for local governance in `fitz-sage`: decide whether
|
| 26 |
retrieved evidence is sufficient, insufficient, or disputed, and expose
|
| 27 |
-
actionable retrieval/failure metadata.
|
|
|
|
|
|
|
| 28 |
|
| 29 |
## Inputs
|
| 30 |
|
|
@@ -38,11 +40,8 @@ Sources:
|
|
| 38 |
[2] <retrieved source text>
|
| 39 |
```
|
| 40 |
|
| 41 |
-
|
| 42 |
-
|
| 43 |
-
```text
|
| 44 |
-
Question: <user query>
|
| 45 |
-
```
|
| 46 |
|
| 47 |
## Output Decoding
|
| 48 |
|
|
|
|
| 24 |
|
| 25 |
The model is intended for local governance in `fitz-sage`: decide whether
|
| 26 |
retrieved evidence is sufficient, insufficient, or disputed, and expose
|
| 27 |
+
actionable retrieval/failure metadata. In `fitz-sage`, v2 g1 is used for
|
| 28 |
+
post-retrieval evidence governance. Query-only pre-retrieval planning remains
|
| 29 |
+
disabled until a query-trained v2 head is available.
|
| 30 |
|
| 31 |
## Inputs
|
| 32 |
|
|
|
|
| 40 |
[2] <retrieved source text>
|
| 41 |
```
|
| 42 |
|
| 43 |
+
The raw model can be run on query-only text, but `fitz-sage` does not use those
|
| 44 |
+
logits for first-pass retrieval planning in this release.
|
|
|
|
|
|
|
|
|
|
| 45 |
|
| 46 |
## Output Decoding
|
| 47 |
|